Anthropic just shipped Claude Sonnet 4.5, and the headline number isn't the benchmark score, it's the...
Anthropic Drops Claude Sonnet 4.5: Extended Thinking Hits 200K Context for Agentic Coding
Anthropic just shipped Claude Sonnet 4.5, and the headline number isn't the benchmark score, it's the...
I keep coming back to one small question: why do we ask a model to write a paragraph when all our...
Seven posts about the heater room on one page: the idea, the log, four models, the test against Claude and the planner. Enough to start at the eighth.
The fifth client on the hot path. Zig 0.17's standard library has HTTP, TLS, JSON and a TZif parser, and the static binary it produces is 488 KB with 2 MB of peak memory. Why that ...